Railway power supply fault diagnosis method and system

Abstract

The embodiment of the invention relates to the technical field of railway power supply, and discloses a railway power supply fault diagnosis method and system.The method comprises the steps that firstly, monitoring data of a first transformer monitor and monitoring data of a second transformer monitor are obtained, and the second monitoring data adopt different storage modes according to different train network states; the network state is stored in the train local data when not meeting the preset condition, and is directly stored in the cloud server when meeting the preset condition. Cleaning the obtained data to obtain target monitoring data, and inputting the target monitoring data into a pre-trained fault diagnosis model for evaluation; and obtaining a fault diagnosis result at least comprising a first diagnosis result (indicating that the second transformer has no power supply fault currently or the fault is not influenced by the first transformer) and a second diagnosis result (indicating that the current power supply fault of the second transformer is influenced by the first transformer). And if the diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer to strive to convert the power supply adjustment control instruction into the first diagnosis result.

Description

Technical Field

[0001] The present invention relates to the technical field of railway power supply, and in particular to a railway power supply fault diagnosis method and system. Background Art

[0002] Railways are an important part of modern transportation, and the stable operation of their power supply systems is crucial to ensuring the safety, efficiency and punctuality of railway transportation. Railway power supply fault diagnosis systems are usually composed of multiple transformers, complex power supply networks and related electrical equipment. The first transformer is responsible for boosting the voltage of the city power supply to meet the long-distance power supply needs of the railway, while the second transformer is responsible for stepping down the railway power supply network to provide suitable voltage for the train. However, due to the long railway lines, numerous equipment and complex and changeable operating environment, the power supply system is prone to various faults, which will not only affect the normal operation of the train, but may even cause safety accidents, bringing huge economic losses and adverse social impacts to railway operations.

[0003] Traditional railway power supply fault diagnosis mainly relies on manual inspection and experience judgment. Operation and maintenance personnel need to regularly conduct on-site inspections of transformers and other equipment to discover potential fault hazards by observing the appearance of the equipment and measuring electrical parameters. This method has many disadvantages: for example, it is inefficient, manual inspections require a lot of time and manpower, and it is difficult to achieve real-time monitoring and rapid diagnosis of the power supply system. Summary of the invention

[0004] The main purpose of the present invention is to provide a railway power supply fault diagnosis method and system, aiming to solve the technical problem of low fault detection efficiency caused by reliance on manual inspection and experience judgment in the prior art.

[0005] To achieve the above-mentioned purpose, in a first aspect, a railway power supply fault diagnosis method is provided in an embodiment of the present application, which is applied to a railway power supply fault diagnosis system, wherein the railway power supply fault diagnosis system includes a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data middle station, and a cloud server, wherein the first transformer is used to boost the mains to supply power to the railway, and the second transformer is used to step down the railway power supply network to supply power to the train, and the method includes: Acquire monitoring data of a first transformer monitor and monitoring data of a second transformer monitor to obtain first monitoring data and second monitoring data, wherein the second monitoring data includes first sub-monitoring data when the network status of the train does not meet a preset condition and second sub-monitoring data when the network status of the train meets a preset condition, the first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train local data middle station, and the second sub-monitoring data is monitoring data collected by the second transformer monitor and directly stored in the cloud server; Performing data cleaning on the first monitoring data and the second monitoring data to obtain target monitoring data; Input the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result, wherein the fault diagnosis result at least includes a first diagnosis result and a second diagnosis result, the first diagnosis result indicating that there is no power supply fault in the second transformer at present or the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicating that the current power supply fault of the second transformer is affected by the first transformer; When the fault diagnosis result is the second diagnosis result, a power supply adjustment control instruction is sent to the first transformer so that the second diagnosis result is changed into the first diagnosis result.

[0006] In a possible implementation, before acquiring the monitoring data of the first transformer monitor and the monitoring data of the second transformer monitor to obtain the first monitoring data and the second monitoring data, the method further includes: According to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to monitor the transformer status data; Acquire a network status of a target train corresponding to the second transformer, wherein the network status includes a normal network status and an abnormal network status; When the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor is temporarily stored in the train local data center to obtain the first sub-monitoring data; When the network status of the target train is normal, the monitoring data collected by the second transformer monitor is directly sent to and stored in the cloud server to obtain second sub-monitoring data.

[0007] In a possible implementation, starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction includes: After starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the fluctuation amplitude of the transformer status data; When the fluctuation range of the transformer status data is greater than or equal to the threshold, the sampling frequency is increased; when the fluctuation range of the transformer status data is less than the threshold, the sampling frequency is reduced or the preset sampling frequency is maintained.

[0008] In a possible implementation, starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction includes: After starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the vibration state of the target train; When the vibration frequency of the target train is greater than or equal to the frequency threshold, the sampling frequency is increased; when the vibration frequency of the target train is less than the frequency threshold, the sampling frequency is reduced or the preset sampling frequency is maintained.

[0009] In a possible implementation, when the network status of the target train is abnormal, temporarily storing the monitoring data collected by the second transformer monitor in the train local data center to obtain the first sub-monitoring data includes: Acquire the local storage capacity of the train local data center in real time. When the local storage capacity reaches a preset threshold, selectively screen the local storage data of the train local data center according to the data collection time sequence or importance level to obtain the data to be processed; The first sub-monitoring data is quickly analyzed by a lightweight analysis unit of the train local data center, and key feature information in the analysis result is extracted and saved; After the analysis is completed, the data to be processed is deleted or compressed and stored.

[0010] In a possible implementation manner, obtaining the network status of the target train corresponding to the second transformer includes: Obtaining signal strength parameters, bandwidth parameters, and delay parameters of the target train network link; Inputting the signal strength parameter, bandwidth parameter and delay parameter of the target train network link into a network status evaluation model to obtain a comprehensive network status score value; It is determined that the comprehensive score of the network status is less than a preset threshold value, and the target train is determined to be in an abnormal network state; it is determined that the comprehensive score of the network status is greater than or equal to the preset threshold value, and the target train is determined to be in a normal network state; the network status evaluation model satisfies the following expression: T=β1 *X(S)+β 2 *Y(B)+β 3 *Z(D), where T is the comprehensive score of the network status, functions X(S), Y(B), and Z(D) are normalized processing functions for signal strength, bandwidth, and delay, respectively, and β 1 , β 2 , β 3 are the weight coefficients of the influence of network link signal strength, bandwidth, and delay on network status; among them, , , .

[0011] In a possible implementation, when the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer so that the second diagnosis result is changed into the first diagnosis result includes: When the power supply adjustment control is performed on the first transformer, if the second transformer still has a power supply fault, a power supply fault self-check prompt message is sent to a target train corresponding to the second transformer.

[0012] In a possible implementation, the method further includes: After sending a power supply adjustment control instruction to the first transformer, real-time monitoring of the power supply state change of the second transformer and the transition of the fault diagnosis result; If the power supply state of the second transformer does not change or the fault diagnosis result does not change within a preset time, the first transformer is switched to the third transformer to use the third transformer for railway power supply.

[0013] In a possible implementation, the target monitoring data includes transformer electrical parameter data or transformer environmental parameter data, the electrical parameter data includes the output voltage and current of the transformer, and the transformer environmental parameter data includes the temperature of the transformer. The target monitoring data is input into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on a railway power supply fault diagnosis system to obtain a fault diagnosis result, including: Inputting the electrical parameter data in the target monitoring data into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; and / or, The environmental parameter data in the target monitoring data is input into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result.

[0014] In a second aspect, an embodiment of the present application provides a railway power supply fault diagnosis system, including: a memory and a processor, where the memory is used to store program codes; the processor is used to call the program codes to execute the method described in the first aspect.

[0015] Different from the prior art, the railway power supply fault diagnosis solution provided in the embodiment of the present application has a system composed of a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data center, and a cloud server. The first transformer is responsible for boosting the mains power for railway power supply, and the second transformer steps down the railway power supply network to supply power to the train. In terms of the fault diagnosis method, first, the monitoring data of the first and second transformer monitors are obtained. Among them, the second monitoring data is stored in different ways according to different train network states. When the network state does not meet the preset conditions, it is stored in the train local data center, and when it is met, it is directly stored in the cloud server. Then, the obtained data is cleaned, and after obtaining the target monitoring data, it is input into a pre-trained fault diagnosis model for evaluation to obtain a fault diagnosis result including at least a first diagnosis result (indicating that the second transformer currently has no power supply fault or its fault is not affected by the first transformer) and a second diagnosis result (indicating that the current power supply fault of the second transformer is affected by the first transformer). If the second diagnosis result is diagnosed, a power supply adjustment control instruction is sent to the first transformer to try to change it to the first diagnosis result. If there is still a power supply fault in the second transformer after adjustment, it can be determined at this time that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train, which helps to timely check potential problems of the train itself, further clarify the cause of the fault, improve the efficiency, accuracy, and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0017] Figure 1 It is a schematic diagram of the application scenario of the railway power supply fault diagnosis method in some embodiments of the present application; Figure 2 It is a schematic diagram of the structure of the railway power supply fault diagnosis system in some embodiments of the present application; Figure 3 It is a schematic diagram of the flow of the railway power supply fault diagnosis method in some embodiments of the present application; Figure 4A schematic diagram of a flow chart of a railway power supply fault diagnosis method in other embodiments of the present application; Figure 5 This is a schematic diagram of the hardware structure of a railway power supply fault diagnosis system in some embodiments of the present application.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0021] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] Railways are an important part of modern transportation, and the stable operation of their power supply systems is crucial to ensuring the safety, efficiency and punctuality of railway transportation. Railway power supply fault diagnosis systems are usually composed of multiple transformers, complex power supply networks and related electrical equipment. The first transformer is responsible for boosting the voltage of the city power supply to meet the long-distance power supply needs of the railway, while the second transformer is responsible for stepping down the railway power supply network to provide suitable voltage for the train. However, due to the long railway lines, numerous equipment and complex and changeable operating environment, the power supply system is prone to various faults, which will not only affect the normal operation of the train, but may even cause safety accidents, bringing huge economic losses and adverse social impacts to railway operations.

[0023] Traditional railway power supply fault diagnosis mainly relies on manual inspection and experience judgment. Operation and maintenance personnel need to regularly conduct on-site inspections of transformers and other equipment to discover potential fault hazards by observing the appearance of the equipment and measuring electrical parameters. This method has many disadvantages: for example, it is inefficient, manual inspections require a lot of time and manpower, and it is difficult to achieve real-time monitoring and rapid diagnosis of the power supply system.

[0024] like Figure 1 As shown, this figure is a schematic diagram of the application scenario of the railway power supply fault diagnosis method in some embodiments of the present application. It should be noted that this figure is a simplified schematic diagram of the railway power supply principle. In the figure, the first transformer 100 serves as the main transformer, and the third transformer 500 serves as the standby transformer, both of which are used to boost the city power supply to achieve railway power supply. Among them, S1 represents the railway power supply network, S3 is the train pantograph, and S2 represents the rails. The train 300 is equipped with a second transformer 200, whose function is to step down the power transmitted by the railway power supply network S1, so as to provide suitable power for the train 300.

[0025] To solve the above problems, Figure 2 As shown, Figure 2 This is a structural diagram of a railway power supply fault diagnosis system in some embodiments of the present application. An embodiment of the present application provides a railway power supply fault diagnosis system, which includes a first transformer 100, a first transformer monitor 110, a first wireless gateway 120, a second transformer 200, a second transformer monitor 210, a second wireless gateway 220, a train local data center 310 and a cloud server 400.

[0026] Among them, the first transformer monitor 110 is used to collect the status data of the first transformer 100, and the second transformer monitor 210 is used to collect the status data of the second transformer 200. The status data may include electrical parameter data, such as transformer output voltage, current, etc., and may also include environmental parameter data, such as transformer temperature. It can also be transformer image data, etc. The first wireless gateway 120 is used to send the status data of the first transformer 100 collected by the first transformer monitor 110 to the cloud server 400. The train local data middle station 310 is used to receive and temporarily store the status data of the second transformer 200 collected by the second transformer monitor 210 when the train network status does not meet the preset conditions. The second wireless gateway 220 is used to send the status data of the second transformer 200 collected by the second transformer monitor 210 and the data temporarily stored in the train local data middle station 310 to the cloud server 400 when the train network status meets the preset conditions. The cloud server 400 is used to process the received data to obtain target monitoring data, and input the target monitoring data into the pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result. The fault diagnosis result includes at least a first diagnosis result and a second diagnosis result. The first diagnosis result indicates that there is no power supply fault in the second transformer at present or the current power supply fault of the second transformer is not affected by the first transformer. The second diagnosis result indicates that the current power supply fault of the second transformer is affected by the first transformer.

[0027] like Figure 1-Figure 4 As shown, the following takes the railway power supply fault diagnosis system executing the railway power supply fault diagnosis method as an example for explanation. It should be noted that although the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from here. Figure 3 The method includes the following steps S200 to S800: Step S200: Acquire monitoring data of the first transformer monitor and monitoring data of the second transformer monitor to obtain first monitoring data and second monitoring data, wherein the second monitoring data includes first sub-monitoring data when the network status of the train does not meet the preset conditions and second sub-monitoring data when the network status of the train meets the preset conditions, the first sub-monitoring data is the monitoring data collected by the second transformer monitor and temporarily stored in the local data center of the train, and the second sub-monitoring data is the monitoring data collected by the second transformer monitor and directly stored in the cloud server; It can be understood that the first monitoring data and the second monitoring data are the data basis for railway power supply fault diagnosis, that is, the first monitoring data and the second monitoring data can provide an accurate data basis for the fault status diagnosis of the first transformer and the second transformer. The present application uses the powerful computing power and advanced diagnostic models of the cloud server to perform fault diagnosis on the railway power supply system. However, the first monitoring data and the second monitoring data are usually local data, and because the train is in a moving state, the second monitoring data is easily affected by the current network state of the train during transmission. Therefore, in order to prevent the loss or packet loss or damage of the second monitoring data during transmission, in one embodiment, the step S200: obtaining the monitoring data of the first transformer monitor and the monitoring data of the second transformer monitor before obtaining the first monitoring data and the second monitoring data, also includes: Step S110, starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction; Step S120, obtaining a network status of a target train corresponding to the second transformer, wherein the network status includes a normal network status and an abnormal network status; Step S130: When the network status of the target train is abnormal, temporarily storing the monitoring data collected by the second transformer monitor in the train local data center to obtain first sub-monitoring data; Step S140: When the network status of the target train is normal, the monitoring data collected by the second transformer monitor is directly sent to and stored in the cloud server to obtain second sub-monitoring data.

[0028] Specifically, first, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to collect the status data of the transformer. This is the basis of the entire data processing process. While collecting data, the network status of the target train corresponding to the second transformer is obtained. The network status is divided into normal state and abnormal state. If the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor will not be sent to the cloud server immediately. Instead, these data will be temporarily stored in the local data center of the train to form the first sub-monitoring data. This can prevent data loss or damage in the case of unstable network. If the network status of the target train is normal, the monitoring data collected by the second transformer monitor will be directly sent to the cloud server and stored on the cloud server to form the second sub-monitoring data. After completing the above steps, the monitoring data of the first transformer monitor (i.e., the first monitoring data) and the monitoring data of the second transformer monitor (including the first sub-monitoring data and the second sub-monitoring data, which are combined as the second monitoring data) can be obtained. These data will be used in the subsequent fault diagnosis process.

[0029] In one embodiment, the step S110, starting the first transformer monitor and the second transformer monitor to monitor the transformer status data according to the railway power supply fault diagnosis instruction, includes: after starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the fluctuation amplitude of the transformer status data; increasing the sampling frequency when the fluctuation amplitude of the transformer status data is greater than or equal to a threshold, and reducing the sampling frequency or maintaining the preset adoption frequency when the fluctuation amplitude of the transformer status data is less than the threshold.

[0030] Specifically, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to collect the status data of the transformer. After the monitor is started, the sampling frequency can be dynamically adjusted according to the fluctuation amplitude of the transformer status data. When the fluctuation amplitude of the transformer status data is greater than or equal to the preset threshold, the sampling frequency is increased. In this way, it can be ensured that when the transformer state changes significantly, more data points can be captured, thereby more accurately reflecting the actual state of the transformer. When the fluctuation amplitude of the transformer status data is less than the threshold, the sampling frequency is reduced or the preset sampling frequency is maintained. In this way, unnecessary data collection can be reduced, the load of data transmission can be reduced, and the efficiency of data processing can be improved. In other embodiments, the sampling frequency can also be adjusted according to the train network state. For example, when the train network state is good (for example, the network delay is low and the packet loss rate is low), the sampling frequency can be appropriately increased so that the transformer status data can be collected more frequently, thereby more accurately reflecting the real-time state of the transformer. When the train network state is not good (for example, the network delay is high and the packet loss rate is high), in order to reduce the failure rate and load of data transmission, the sampling frequency can be appropriately reduced. In this way, unnecessary data collection and transmission can be reduced, and the efficiency of data processing can be improved.

[0031] In another embodiment, the step S110: starting the first transformer monitor and the second transformer monitor to monitor the transformer status data according to the railway power supply fault diagnosis instruction, includes: after starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the vibration state of the target train; increasing the sampling frequency when the vibration frequency of the target train is greater than or equal to the frequency threshold, and reducing the sampling frequency or maintaining the preset adopted frequency when the vibration frequency of the target train is less than the frequency threshold.

[0032] Specifically, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to start collecting transformer status data. After starting the monitor, the vibration state of the target train is monitored at the same time. For example, this can be achieved by a vibration sensor installed on the train. When the vibration frequency of the train is greater than or equal to the preset frequency threshold, it indicates that the train may be in an unstable or high-speed driving state. At this time, the sampling frequency of the transformer monitor should be increased. In this way, data can be collected more frequently to capture the changes in the transformer state that may be caused by vibration. When the vibration frequency of the train is less than the frequency threshold, it indicates that the train is in a relatively stable or low-speed driving state. At this time, the sampling frequency can be appropriately reduced or the preset sampling frequency can be maintained. This can reduce unnecessary data collection and reduce the load of data processing.

[0033] In one embodiment, the step S130: when the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor is temporarily stored in the train local data center to obtain the first sub-monitoring data, including: obtaining the local storage capacity of the train local data center in real time, and when the local storage capacity reaches a preset threshold, selectively screening the local storage data of the train local data center according to the data collection time sequence or importance level to obtain the data to be processed; quickly analyzing the first sub-monitoring data through the lightweight analysis unit of the train local data center, and extracting and saving the key feature information in the analysis results; deleting or compressing the data to be processed after the analysis is completed.

[0034] Specifically, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to collect transformer status data. While collecting data, it is determined whether the network status of the target train is abnormal. When the train network status is abnormal, the local storage capacity information of the train local data center is obtained in real time. When the local storage capacity reaches the preset threshold, in order to avoid data overflow or loss, the local storage data of the train local data center can be selectively screened according to the data collection time sequence or importance level. In this way, it can be ensured that the latest or most important data is retained, while the older or less important data is deleted or compressed. In order to prevent data deletion from affecting the data analysis results, the lightweight analysis unit of the train local data center can be used to quickly analyze the first sub-monitoring data first. The purpose of the analysis is to extract key feature information from the data, which is crucial for subsequent fault diagnosis (providing a certain reference basis for subsequent complete data analysis). The extracted key feature information can be saved separately for quick access when needed. After the analysis is completed, the screened data to be processed is deleted or compressed for storage. The deletion operation can free up storage space, while compressed storage can reduce the space occupied by data while retaining the integrity of the data.

[0035] In one embodiment, the step S120: obtaining the network status of the target train corresponding to the second transformer includes: obtaining the signal strength parameter, bandwidth parameter and delay parameter of the target train network link; inputting the signal strength parameter, bandwidth parameter and delay parameter of the target train network link into the network status evaluation model to obtain a comprehensive network status score; determining that the comprehensive network status score is less than a preset threshold, determining that the target train is in an abnormal network state; determining that the comprehensive network status score is greater than or equal to a preset threshold, determining that the target train is in a normal network state; the network status evaluation model satisfies the following expression: T=β 1 *X(S)+β 2 *Y(B)+β 3 *Z(D), where T is the comprehensive score of the network status, functions X(S), Y(B), and Z(D) are normalized processing functions for signal strength, bandwidth, and delay, respectively, and β 1 , β 2 , β 3 They are the weight coefficients of the impact of network link signal strength, bandwidth, and delay on the network status.

[0036] In one embodiment, functions X(S), Y(B), and Z(D) are respectively expressed as follows: , , .

[0037] Specifically, when the signal strength S is less than or equal to the minimum signal strength S min When X(S)=0, it means that if the signal strength is lower than a certain lower limit, its normalized score is 0. min and the maximum signal strength S max When the signal strength S is greater than or equal to the maximum signal strength S max When X(S) = 1, it means that if the signal strength is above a certain upper limit, its normalized score is 1. Since the bandwidth B has a very large range of values, from very low bandwidth (such as a few kbps) to very high bandwidth (such as a few Gbps or even higher), the use of a logarithmic function can compress such a large range of data into a relatively small range, which is convenient for processing and comparison. The normalization process is similar to the normalization process of signal strength and will not be repeated here. Similarly, the normalization process of delay will not be repeated. It can be understood that when the comprehensive score of the network status exceeds the preset threshold, it indicates that the network status of the train is normal. When the comprehensive score of the network status is lower than the preset threshold, it indicates that the network status of the train is abnormal.

[0038] It should be noted that, since the transformer monitor may collect large-capacity data such as images, such data transmission has high bandwidth requirements. 2 The value of β can make the network status evaluation model more reasonable, that is, 1 is 0.3, β 2 is 0.4, β 3 is 0.3.

[0039] In the embodiment of the present application, by combining the normalized processing functions of signal strength, bandwidth, and delay with their respective weight coefficients, the network status assessment model can comprehensively consider the impact of these three key network parameters on the train network status, so that it can simply and effectively determine whether the train is in a normal network state, providing a strong basis for train network management and power supply fault diagnosis.

[0040] Step S400: performing data cleaning processing on the first monitoring data and the second monitoring data to obtain target monitoring data; Specifically, data cleaning may include but is not limited to processing duplicate records, missing data, outliers or erroneous data. For example, a processing strategy can be formulated for missing data based on the missing ratio and field importance. Unimportant fields or data with too high missing rates are directly deleted. Important fields or data with acceptable missing rates are supplemented. Supplementation methods include mean supplementation, median supplementation, mode supplementation, interpolation or prediction model supplementation.

[0041] Step S600: inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result, wherein the fault diagnosis result at least includes a first diagnosis result and a second diagnosis result, the first diagnosis result indicating that the second transformer currently has no power supply fault or the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicating that the current power supply fault of the second transformer is affected by the first transformer; In one embodiment, the target monitoring data includes transformer electrical parameter data or transformer environmental parameter data, the electrical parameter data includes the output voltage and current of the transformer, and the transformer environmental parameter data includes the temperature of the transformer. The step S600: inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result, including: inputting the electrical parameter data in the target monitoring data into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; and / or, inputting the environmental parameter data in the target monitoring data into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result.

[0042] Specifically, the electrical parameter data in the target monitoring data can be input into the pre-trained first sub-fault diagnosis model, so as to carry out the electrical parameter fault diagnosis evaluation of the railway power supply fault diagnosis system, and then obtain the corresponding fault diagnosis results; and / or, the environmental parameter data in the target monitoring data can be input into the pre-trained second sub-fault diagnosis model, so as to carry out the environmental parameter fault diagnosis evaluation of the railway power supply fault diagnosis system, and finally obtain the relevant fault diagnosis results. In this way, it is possible to carry out the diagnosis evaluation more specifically based on different types of parameter data using the special sub-fault diagnosis model, improve the accuracy and effectiveness of the fault diagnosis, and provide more reliable guarantee and support for the stable operation of the railway power supply system.

[0043] For example, assume that in a railway power supply system, the first transformer (main transformer) operates normally, its output voltage is stable at the rated value, and the current is also within the normal range. The electrical parameter data monitored by the second transformer (transformer in the train) are as follows: the output voltage is 80% of the normal supply voltage, and the current is slightly higher than that in normal operation. At the same time, the environmental parameter data shows that the temperature of the second transformer is 60 degrees Celsius, which is within the normal operating temperature range. These electrical parameter data are input into the pre-trained first sub-fault diagnosis model. After analysis and calculation, the model finds that the reduction in the output voltage of the second transformer may be caused by a sudden increase in the train's own load (such as a large number of passengers using high-power electrical appliances at the same time), and the increase in current is also a normal reaction to the increase in load, and the output voltage and current of the first transformer are normal, thereby obtaining the first diagnostic result, that is, the second transformer currently does not have a power supply fault or its current power supply fault is not affected by the first transformer.

[0044] For another example, the output voltage of the first transformer suddenly dropped by 20%, and the output voltage of the second transformer also dropped significantly, making it almost impossible to supply power to the train normally. At the same time, the current of the second transformer fluctuated abnormally, and the transformer temperature in the environmental parameters rose rapidly. After inputting these data into the first sub-fault diagnosis model and the second sub-fault diagnosis model respectively, the first sub-fault diagnosis model found that the fault of the second transformer was obviously related to the abnormal drop in the output voltage of the first transformer, and the second sub-fault diagnosis model did not detect the fault caused by the environmental factors of the second transformer itself, thus obtaining the second diagnosis result, that is, the current power supply fault of the second transformer was affected by the first transformer.

[0045] Step S800: When the fault diagnosis result is a second diagnosis result, a power supply adjustment control instruction is sent to the first transformer so that the second diagnosis result is changed into the first diagnosis result.

[0046] After sending a power supply adjustment control instruction to the first transformer in an effort to convert it into the first diagnosis result, two results may occur, namely, the second transformer resumes normal power supply or the second transformer still has a power supply fault. Therefore, in one embodiment, after sending a power supply adjustment control instruction to the first transformer, the power supply state change of the second transformer and the change of the fault diagnosis result can be monitored in real time; if the second transformer resumes normal power supply within the preset time, no further measures are required. If the power supply state of the second transformer does not change or the fault diagnosis result does not change within the preset time (the second transformer still has a power supply fault), it may be that the power supply fault of the first transformer cannot be automatically eliminated. At this time, the first transformer can be switched to a third transformer to use the third transformer for railway power supply.

[0047] In another embodiment, the step S800: when the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer to change the second diagnosis result into the first diagnosis result, including: when the power supply adjustment control is performed on the first transformer, if the second transformer still has a power supply fault, sending a power supply fault self-check prompt information to the target train corresponding to the second transformer.

[0048] Specifically, if the diagnosis is the second diagnosis result, a power supply adjustment control instruction is sent to the first transformer, striving to convert it into the first diagnosis result. If the second transformer still has a power supply fault after the adjustment, it can be determined that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train, which helps to timely check the potential problems of the train itself, further clarify the cause of the fault, improve the accuracy and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system.

[0049] Based on this, the railway power supply fault diagnosis scheme provided by the embodiment of the present application is composed of a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data middle station and a cloud server. The first transformer is responsible for boosting the city power supply for railway power supply, and the second transformer is responsible for stepping down the railway power supply network for train power supply. In the fault diagnosis method, the monitoring data of the first and second transformer monitors are first obtained, wherein the second monitoring data is stored in different ways according to the different train network states, and is stored in the train local data middle station when the network state does not meet the preset conditions, and is directly stored in the cloud server when it meets the conditions. Then, the acquired data is cleaned, and the target monitoring data is obtained and input into the pre-trained fault diagnosis model for evaluation, and a fault diagnosis result including at least the first diagnosis result (indicating that the second transformer currently has no power supply fault or its fault is not affected by the first transformer) and the second diagnosis result (indicating that the current power supply fault of the second transformer is affected by the first transformer) is obtained. If the diagnosis is the second diagnosis result, a power supply adjustment control instruction is sent to the first transformer, and it is attempted to be converted into the first diagnosis result. If the second transformer still has a power supply fault after adjustment, it can be determined that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train. This will help to promptly check the train's own potential problems, further clarify the cause of the fault, improve the efficiency, accuracy and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system.

[0050] like Figure 5 As shown, Figure 5This is a schematic diagram of the hardware structure of a railway power supply fault diagnosis system in some embodiments of the present application. The railway power supply fault diagnosis system provided in the embodiments of the present application also includes a memory 1000 and a processor 2000, wherein the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the railway power supply fault diagnosis method as described above.

[0051] Among them, the processor 2000 is used to provide computing and control capabilities to control the railway power supply fault diagnosis system to perform corresponding tasks, for example, to control the railway power supply fault diagnosis system to perform the railway power supply fault diagnosis method in any of the above method embodiments, the method comprising: acquiring monitoring data of a first transformer monitor and monitoring data of a second transformer monitor to obtain first monitoring data and second monitoring data, wherein the second monitoring data comprises first sub-monitoring data when the network status of the train does not meet a preset condition and second sub-monitoring data when the network status of the train meets a preset condition, the first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train local data center, and the second sub-monitoring data is monitoring data collected and directly stored by the second transformer monitor. monitoring data on a cloud server; performing data cleaning processing on the first monitoring data and the second monitoring data to obtain target monitoring data; inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on a railway power supply fault diagnosis system to obtain a fault diagnosis result, wherein the fault diagnosis result includes at least a first diagnosis result and a second diagnosis result, the first diagnosis result indicating that there is currently no power supply fault in the second transformer or that the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicating that the current power supply fault of the second transformer is affected by the first transformer; when the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer to change the second diagnosis result into the first diagnosis result.

[0052] The processor 2000 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or any combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0053] The memory 1000, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the railway power supply fault diagnosis method in the embodiment of the present application. The processor 2000 can implement the railway power supply fault diagnosis method in any of the above method embodiments by running the non-transient software programs, instructions and modules stored in the memory 1000.

[0054] Specifically, the memory 1000 may include a volatile memory (VM), such as a random access memory (RAM); the memory 1000 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD) or other non-transitory solid-state storage device; the memory 1000 may also include a combination of the above-mentioned types of memory.

[0055] In summary, the railway power supply fault diagnosis system of the present application adopts the technical solution of any one of the above-mentioned railway power supply fault diagnosis method embodiments, and therefore, has at least the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be described one by one here.

[0056] The embodiment of the present application also provides a computer-readable storage medium, such as a memory including a program code, and the program code can be executed by a processor to complete the railway power supply fault diagnosis method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0057] The present application also provides a computer program product, which includes one or more program codes, which are stored in a computer-readable storage medium. The processor of the railway power supply fault diagnosis system reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the railway power supply fault diagnosis method provided in the above embodiment.

[0058] A person skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be accomplished by hardware or by hardware associated with a program code, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0059] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or by hardware. It can be understood by those skilled in the art that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0061] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A railway power supply fault diagnosis method, characterized in that: Applied to a railway power supply fault diagnosis system, the railway power supply fault diagnosis system includes a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data center and a cloud server, the first transformer is used to boost the mains to supply power to the railway, the second transformer is used to step down the railway power supply network to supply power to the train, and the method includes: Acquire monitoring data of a first transformer monitor and monitoring data of a second transformer monitor to obtain first monitoring data and second monitoring data, wherein the second monitoring data includes first sub-monitoring data when the network status of the train does not meet a preset condition and second sub-monitoring data when the network status of the train meets a preset condition, the first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train local data middle station, and the second sub-monitoring data is monitoring data collected by the second transformer monitor and directly stored in the cloud server; Performing data cleaning on the first monitoring data and the second monitoring data to obtain target monitoring data; The target monitoring data is input into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; wherein the fault diagnosis result includes at least a first diagnosis result and a second diagnosis result, the first diagnosis result indicating that there is no power supply fault in the second transformer at present or the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicating that the current power supply fault of the second transformer is affected by the first transformer; When the fault diagnosis result is the second diagnosis result, a power supply adjustment control instruction is sent to the first transformer so that the second diagnosis result is changed into the first diagnosis result.

2. The railway power supply fault diagnosis method according to claim 1, characterized in that: Before obtaining the monitoring data of the first transformer monitor and the monitoring data of the second transformer monitor to obtain the first monitoring data and the second monitoring data, the method further includes: According to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are started to monitor the transformer status data; Acquire a network status of a target train corresponding to the second transformer, wherein the network status includes a normal network status and an abnormal network status; When the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor is temporarily stored in the train local data center to obtain the first sub-monitoring data; When the network status of the target train is normal, the monitoring data collected by the second transformer monitor is directly sent to and stored in the cloud server to obtain second sub-monitoring data.

3. The railway power supply fault diagnosis method according to claim 2, characterized in that: The starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction includes: After starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the fluctuation amplitude of the transformer status data; When the fluctuation range of the transformer status data is greater than or equal to the threshold, the sampling frequency is increased; when the fluctuation range of the transformer status data is less than the threshold, the sampling frequency is reduced or the preset sampling frequency is maintained.

4. The railway power supply fault diagnosis method according to claim 2, characterized in that: The starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction includes: After starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the vibration state of the target train; When the vibration frequency of the target train is greater than or equal to the frequency threshold, the sampling frequency is increased; when the vibration frequency of the target train is less than the frequency threshold, the sampling frequency is reduced or the preset sampling frequency is maintained.

5. The railway power supply fault diagnosis method according to claim 2, characterized in that: When the network status of the target train is abnormal, temporarily storing the monitoring data collected by the second transformer monitor in the train local data center to obtain the first sub-monitoring data includes: Acquire the local storage capacity of the train local data center in real time. When the local storage capacity reaches a preset threshold, selectively screen the local storage data of the train local data center according to the data collection time sequence or importance level to obtain the data to be processed; The first sub-monitoring data is quickly analyzed by a lightweight analysis unit of the train local data center, and key feature information in the analysis result is extracted and saved; After the analysis is completed, the data to be processed is deleted or compressed and stored.

6. The railway power supply fault diagnosis method according to claim 2, characterized in that: The obtaining the network status of the target train corresponding to the second transformer includes: Obtaining signal strength parameters, bandwidth parameters, and delay parameters of the target train network link; Inputting the signal strength parameter, bandwidth parameter and delay parameter of the target train network link into a network status evaluation model to obtain a comprehensive network status score value; It is determined that the comprehensive score of the network status is less than a preset threshold value, and the target train is determined to be in an abnormal network state; it is determined that the comprehensive score of the network status is greater than or equal to the preset threshold value, and the target train is determined to be in a normal network state; the network status evaluation model satisfies the following expression: T=β1*X(S)+β2*Y(B)+β3*Z(D), where T is the comprehensive score of the network status, functions X(S), Y(B), and Z(D) are normalized processing functions of signal strength, bandwidth, and delay, respectively, and β1, β2, and β3 are the weight coefficients of the influence of network link signal strength, bandwidth, and delay on the network status, respectively; where, ， ， 。 7. The railway power supply fault diagnosis method according to claim 1, characterized in that: When the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer so that the second diagnosis result is changed into the first diagnosis result includes: When the power supply adjustment control is performed on the first transformer, if the second transformer still has a power supply fault, a power supply fault self-check prompt message is sent to a target train corresponding to the second transformer.

8. The railway power supply fault diagnosis method according to claim 1, characterized in that: The method further comprises: After sending a power supply adjustment control instruction to the first transformer, real-time monitoring of the power supply state change of the second transformer and the transition of the fault diagnosis result; If the power supply state of the second transformer does not change or the fault diagnosis result does not change within a preset time, the first transformer is switched to the third transformer to use the third transformer for railway power supply.

9. The railway power supply fault diagnosis method according to claim 1, characterized in that: The target monitoring data includes transformer electrical parameter data or transformer environmental parameter data, the electrical parameter data includes the output voltage and current of the transformer, and the transformer environmental parameter data includes the temperature of the transformer. The target monitoring data is input into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result, including: Inputting the electrical parameter data in the target monitoring data into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; and / or, The environmental parameter data in the target monitoring data is input into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result.

10. A railway power supply fault diagnosis system, characterized in that: include: A memory and a processor, wherein the memory is used to store program codes; The processor is used to call the program code to execute the method according to any one of claims 1 to 9.

Images